Effective and fast localization of anatomical structures is a crucial ﬁrst step towards automated analysis of medical volumes. In this paper, we propose an iterative approach for structure localization in medical volumes based on the adaptive bandwidth mean-shift algorithm for object detection (ABMSOD). We extend and tune the ABMSOD algorithm, originally used to detect 2D objects in non-medical images, to localize 3Danatomical structures in medical volumes. For fast localization, we design and develop optimized parallel implementations of the proposed algorithm on multi-cores using Open MP, and on GPUs using CUDA. We evaluate the quality, performance and scalability of the proposed algorithm on Computed Tomography (CT) volumes for various structures.
Automation of clinical procedures involving analysis of imaging data, such as tissue volume quantiﬁcation, screening, diagnosis as well as surgical procedures, not only helps to improve patient throughput but also enhances repeatability, safety and quality of patient care. Typically, analysis of medical imaging data includes operations such as image segmentation, registration, feature extraction, recognition and classiﬁcation. As medical images suffer from inherent noise and low contrast and spatial resolution , accurate segmentation, registration or classiﬁcation is difﬁcult and computationally intensive. For example, several 3D anatomy segmentation and recognition algorithms take several minutes for execution even with GPU acceleration. In addition, these algorithms are highly tuned and speciﬁc to an anatomical structure, like the lung or liver. To address the above issues, a generic pre-processing step that localizes any structure can be very useful in improving both speed and accuracy of the above procedures. For example, high precision segmentation of tumors can be accomplished faster by executing complex domain-speciﬁc segmentation algorithms on a localized region around the tumor, rather than the entire volume.
Localization can be used to improve the speed and quality of diagnosis for difﬁcult cases. A doctor can scan his past patient data to retrieve a subset of imaging records that comprise of the structure of interest. Domain-speciﬁc algorithms can then be run on localized regions in the relevant records to identify similar cases quickly, which the doctor can consult before making critical diagnoses.